DeepMPTB: a vaginal microbiome-based deep neural network as artificial intelligence strategy for efficient preterm birth prediction
Abstract In recent decades, preterm birth (PTB) has become a significant research focus in the healthcare field, as it is a leading cause of neonatal mortality worldwide. Using five independent study cohorts including 1290 vaginal samples from 561 pregnant women who delivered at term (n = 1029) or p...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2024-02-01
|
| Series: | Biomarker Research |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40364-024-00557-1 |
| _version_ | 1827326676025999360 |
|---|---|
| author | Oshma Chakoory Vincent Barra Emmanuelle Rochette Loïc Blanchon Vincent Sapin Etienne Merlin Maguelonne Pons Denis Gallot Sophie Comtet-Marre Pierre Peyret |
| author_facet | Oshma Chakoory Vincent Barra Emmanuelle Rochette Loïc Blanchon Vincent Sapin Etienne Merlin Maguelonne Pons Denis Gallot Sophie Comtet-Marre Pierre Peyret |
| author_sort | Oshma Chakoory |
| collection | DOAJ |
| description | Abstract In recent decades, preterm birth (PTB) has become a significant research focus in the healthcare field, as it is a leading cause of neonatal mortality worldwide. Using five independent study cohorts including 1290 vaginal samples from 561 pregnant women who delivered at term (n = 1029) or prematurely (n = 261), we analysed vaginal metagenomics data for precise microbiome structure characterization. Then, a deep neural network (DNN) was trained to predict term birth (TB) and PTB with an accuracy of 84.10% and an area under the receiver operating characteristic curve (AUROC) of 0.875 ± 0.11. During a benchmarking process, we demonstrated that our DL model outperformed seven currently used machine learning algorithms. Finally, our results indicate that overall diversity of the vaginal microbiota should be taken in account to predict PTB and not specific species. This artificial-intelligence based strategy should be highly helpful for clinicians in predicting preterm birth risk, allowing personalized assistance to address various health issues. DeepMPTB is open source and free for academic use. It is licensed under a GNU Affero General Public License 3.0 and is available at https://deepmptb.streamlit.app/ . Source code is available at https://github.com/oschakoory/DeepMPTB and can be easily installed using Docker ( https://www.docker.com/ ). |
| first_indexed | 2024-03-07T14:49:02Z |
| format | Article |
| id | doaj.art-d7036c412bcd4df49d89e46037612c75 |
| institution | Directory Open Access Journal |
| issn | 2050-7771 |
| language | English |
| last_indexed | 2024-03-07T14:49:02Z |
| publishDate | 2024-02-01 |
| publisher | BMC |
| record_format | Article |
| series | Biomarker Research |
| spelling | doaj.art-d7036c412bcd4df49d89e46037612c752024-03-05T19:49:58ZengBMCBiomarker Research2050-77712024-02-011211510.1186/s40364-024-00557-1DeepMPTB: a vaginal microbiome-based deep neural network as artificial intelligence strategy for efficient preterm birth predictionOshma Chakoory0Vincent Barra1Emmanuelle Rochette2Loïc Blanchon3Vincent Sapin4Etienne Merlin5Maguelonne Pons6Denis Gallot7Sophie Comtet-Marre8Pierre Peyret9Université Clermont Auvergne, INRAE, MEDISUniversité Clermont Auvergne, CNRS, Mines de Saint-Étienne, Clermont-Auvergne-INP, LIMOSDepartment of Pediatrics, CRECHE Unit, CHU Clermont-FerrandTeam “Translational approach to epithelial injury and repair”, Université Clermont Auvergne, CNRSTeam “Translational approach to epithelial injury and repair”, Université Clermont Auvergne, CNRSDepartment of Pediatrics, CRECHE Unit, CHU Clermont-FerrandDepartment of Pediatrics, CRECHE Unit, CHU Clermont-FerrandTeam “Translational approach to epithelial injury and repair”, Université Clermont Auvergne, CNRSUniversité Clermont Auvergne, INRAE, MEDISUniversité Clermont Auvergne, INRAE, MEDISAbstract In recent decades, preterm birth (PTB) has become a significant research focus in the healthcare field, as it is a leading cause of neonatal mortality worldwide. Using five independent study cohorts including 1290 vaginal samples from 561 pregnant women who delivered at term (n = 1029) or prematurely (n = 261), we analysed vaginal metagenomics data for precise microbiome structure characterization. Then, a deep neural network (DNN) was trained to predict term birth (TB) and PTB with an accuracy of 84.10% and an area under the receiver operating characteristic curve (AUROC) of 0.875 ± 0.11. During a benchmarking process, we demonstrated that our DL model outperformed seven currently used machine learning algorithms. Finally, our results indicate that overall diversity of the vaginal microbiota should be taken in account to predict PTB and not specific species. This artificial-intelligence based strategy should be highly helpful for clinicians in predicting preterm birth risk, allowing personalized assistance to address various health issues. DeepMPTB is open source and free for academic use. It is licensed under a GNU Affero General Public License 3.0 and is available at https://deepmptb.streamlit.app/ . Source code is available at https://github.com/oschakoory/DeepMPTB and can be easily installed using Docker ( https://www.docker.com/ ).https://doi.org/10.1186/s40364-024-00557-1Preterm birthVaginal microbiomePredictive diagnosisDeep neural networkArtificial intelligenceMachine learning |
| spellingShingle | Oshma Chakoory Vincent Barra Emmanuelle Rochette Loïc Blanchon Vincent Sapin Etienne Merlin Maguelonne Pons Denis Gallot Sophie Comtet-Marre Pierre Peyret DeepMPTB: a vaginal microbiome-based deep neural network as artificial intelligence strategy for efficient preterm birth prediction Biomarker Research Preterm birth Vaginal microbiome Predictive diagnosis Deep neural network Artificial intelligence Machine learning |
| title | DeepMPTB: a vaginal microbiome-based deep neural network as artificial intelligence strategy for efficient preterm birth prediction |
| title_full | DeepMPTB: a vaginal microbiome-based deep neural network as artificial intelligence strategy for efficient preterm birth prediction |
| title_fullStr | DeepMPTB: a vaginal microbiome-based deep neural network as artificial intelligence strategy for efficient preterm birth prediction |
| title_full_unstemmed | DeepMPTB: a vaginal microbiome-based deep neural network as artificial intelligence strategy for efficient preterm birth prediction |
| title_short | DeepMPTB: a vaginal microbiome-based deep neural network as artificial intelligence strategy for efficient preterm birth prediction |
| title_sort | deepmptb a vaginal microbiome based deep neural network as artificial intelligence strategy for efficient preterm birth prediction |
| topic | Preterm birth Vaginal microbiome Predictive diagnosis Deep neural network Artificial intelligence Machine learning |
| url | https://doi.org/10.1186/s40364-024-00557-1 |
| work_keys_str_mv | AT oshmachakoory deepmptbavaginalmicrobiomebaseddeepneuralnetworkasartificialintelligencestrategyforefficientpretermbirthprediction AT vincentbarra deepmptbavaginalmicrobiomebaseddeepneuralnetworkasartificialintelligencestrategyforefficientpretermbirthprediction AT emmanuellerochette deepmptbavaginalmicrobiomebaseddeepneuralnetworkasartificialintelligencestrategyforefficientpretermbirthprediction AT loicblanchon deepmptbavaginalmicrobiomebaseddeepneuralnetworkasartificialintelligencestrategyforefficientpretermbirthprediction AT vincentsapin deepmptbavaginalmicrobiomebaseddeepneuralnetworkasartificialintelligencestrategyforefficientpretermbirthprediction AT etiennemerlin deepmptbavaginalmicrobiomebaseddeepneuralnetworkasartificialintelligencestrategyforefficientpretermbirthprediction AT maguelonnepons deepmptbavaginalmicrobiomebaseddeepneuralnetworkasartificialintelligencestrategyforefficientpretermbirthprediction AT denisgallot deepmptbavaginalmicrobiomebaseddeepneuralnetworkasartificialintelligencestrategyforefficientpretermbirthprediction AT sophiecomtetmarre deepmptbavaginalmicrobiomebaseddeepneuralnetworkasartificialintelligencestrategyforefficientpretermbirthprediction AT pierrepeyret deepmptbavaginalmicrobiomebaseddeepneuralnetworkasartificialintelligencestrategyforefficientpretermbirthprediction |